Actas de congresos
Fine Tuning Deep Boltzmann Machines Through Meta-Heuristic Approaches
Fecha
2018-01-01Registro en:
2018 Ieee 12th International Symposium On Applied Computational Intelligence And Informatics (saci). New York: Ieee, p. 419-424, 2018.
WOS:000448144200073
Autor
Universidade Federal de São Carlos (UFSCar)
Universidade Estadual Paulista (Unesp)
Institución
Resumen
The Deep learning framework has been widely used in different applications from medicine to engineering. However, there is a lack of works that manage to deal with the issue of hyperparameter fine-tuning, since machine learning techniques often require a considerable human effort in this task. In this paper, we propose to fine-tune Deep Boltzmann Machines using meta-heuristic techniques, which do not require the computation of the gradient of the fitness function, that may be insurmountable in high-dimensional optimization spaces. We demonstrate the validity of the proposed approach against Deep Belief Networks concerning binary image reconstruction.